agentcanon-repo
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines a set of shell commands for the agent to execute, including directory creation (
mkdir), moving files (mv,git mv), removing empty directories (rmdir), and creating symbolic links (ln). These commands are standard for the stated task of repository migration and are limited to the local project environment.- [INDIRECT_PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it reads and processes external data from the repository, such as the directory structure and the contents ofSKILL.md,CLAUDE.md, andAGENTS.mdfiles. - Ingestion points: Repository file names, directory structure, and content of instruction files.
- Boundary markers: The instructions explicitly mandate a two-step process where a detailed plan must be presented to and approved by the user before execution.
- Capability inventory: The skill has the capability to move and link files and write merged content to instruction files.
- Sanitization: The safety model relies on human review of the generated plan rather than programmatic sanitization, which is appropriate for this use case.
Audit Metadata